performance measurements

Each table row shows performance measurements for this Erlang HiPE program with a particular command-line input value N.

 N  CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
250,0003.283.31143,164930  1% 2% 0% 100%
2,500,00030.9231.291,103,292930  0% 1% 1% 100%
25,000,000311.33366.543,646,340930  6% 8% 9% 100%

Read the ↓ make, command line, and program output logs to see how this program was run.

Read k-nucleotide benchmark to see what this program should do.

 notes

Erlang/OTP 17 [erts-6.2] [source] [64-bit] [smp:4:4] [async-threads:10] [hipe] [kernel-poll:false]

 k-nucleotide Erlang HiPE program source code

% The Computer Language Benchmarks Game
% http://benchmarksgame.alioth.debian.org/
%% contributed by Fredrik Svahn based on an earlier submission
%%             by Kenneth Johansson, Vlad Dumitrescu and Ulf Wiger

-module(knucleotide).
-export([main/1]).

to_upper(<<C, Cs/binary>>, Acc) when C >= $a, C =< $z ->
    to_upper(Cs, [C-($a-$A)| Acc]);
to_upper(<<$\n, Cs/binary>>, Acc) -> to_upper(Cs, Acc);
to_upper(<<C, Cs/binary>>, Acc) -> to_upper(Cs, [C | Acc]);
to_upper(<<>>, Acc) -> lists:reverse(Acc).

%% Read and discard until start of third segment
seek_three() ->
    case io:get_line('') of
	<<">TH", _/binary>> -> done;
	eof        -> erlang:error(eof);
	_          -> seek_three()
    end.

%% Read third segment
get_seq_three(Seq) ->
    case io:get_line('') of
	eof -> iolist_to_binary(lists:reverse(Seq));
	Str -> get_seq_three([to_upper(Str, [])|Seq])
    end.

%% Generate frequency hash table
gen_freq_table(FreqT, Seq, Len) -> 
    gen_freq_table(Seq, Len, FreqT, size(Seq)-Len).

gen_freq_table(_, _, _, -1) -> done;
gen_freq_table(Seq, Len, FreqT, Dec) ->
    <<_:Dec/binary, Key:Len/binary, _/binary>> = Seq,
    update_counter(Key, FreqT),
    gen_freq_table(Seq, Len, FreqT, Dec-1).

%% Update hash table counter for already existing pattern or insert new
update_counter(Key, FreqT) ->
    try ets:update_counter(FreqT, Key, 1) of _ -> ok
    catch error:badarg -> ets:insert(FreqT, {Key, 1})
    end.

%% Print the frequency table in the right order
print_freq_table(FreqT) ->
    FreqList = lists:reverse(lists:keysort(2, ets:tab2list(FreqT))),
    Tot = lists:foldr(fun({_, Cnt}, Acc)-> Acc + Cnt end, 0, FreqList),
    lists:foreach(fun({Nucleoid, Cnt})->
			  io:fwrite("~s ~.3f\n",[Nucleoid, Cnt*100/Tot]) 
		  end, FreqList),
    io:fwrite("\n").

%% Print number of occurrences for a specific pattern
print_count(FreqT, Pattern) ->
    case ets:lookup(FreqT, Pattern) of
	[{_, Value}] -> io:fwrite("~w\t~s\n",[Value, Pattern]);
	[] -> io:fwrite("~w\t~s\n",[0, Pattern])
    end.

%% Spawn a worker process with its own hash table
do({PrintFun, Pattern}, Seq) ->
    spawn( fun()->
		   FreqT = ets:new(hash, [set]),
		   gen_freq_table(FreqT, Seq, size(Pattern)),
		   %Work is done, wait for token and print
		   receive Pids -> 
			   PrintFun(FreqT, Pattern),
			   hd(Pids) ! tl(Pids) 
		   end,
		   ets:delete(FreqT)
	   end ).

main(_Arg) ->
    io:setopts(standard_io, [binary]),
    seek_three(),
    Seq = get_seq_three([]),
    PrintFreq = fun(Res, _Pattern)-> print_freq_table(Res) end,
    PrintCount = fun(Res, Pattern)-> print_count(Res, Pattern) end,
    Actions = [{PrintFreq,  <<"?">>},
	       {PrintFreq,  <<"??">>},
	       {PrintCount, <<"GGT">>},
	       {PrintCount, <<"GGTA">>},
	       {PrintCount, <<"GGTATT">>},
	       {PrintCount, <<"GGTATTTTAATT">>},
	       {PrintCount, <<"GGTATTTTAATTTATAGT">>}],
	
    Pids = [ do(Action, Seq) || Action <- Actions ],
    %Pass token to print in right order
    hd(Pids) ! tl(Pids) ++ [self()],
    receive _Pid -> halt(0) end.

 make, command-line, and program output logs

Thu, 27 Nov 2014 02:39:07 GMT

MAKE:
mv knucleotide.hipe knucleotide.erl
/usr/local/src/otp_src_17.3_nosmp/bin/erlc +native +"{hipe, [o3]}"  knucleotide.erl
rm knucleotide.erl
0.87s to complete and log all make actions

COMMAND LINE:
/usr/local/src/otp_src_17.3_nosmp/bin/erl -smp disable -noshell -run  knucleotide main 0 < knucleotide-input25000000.txt

PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754

AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902

1471758	GGT
446535	GGTA
47336	GGTATT
893	GGTATTTTAATT
893	GGTATTTTAATTTATAGT

Revised BSD license

  Home   Conclusions   License   Play